diff --git a/include/linux/swap.h b/include/linux/swap.h index b5f6f2916de1..ce7e82cf787f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -337,25 +337,6 @@ struct swap_info_struct { */ }; -#ifdef CONFIG_64BIT -#define SWAP_RA_ORDER_CEILING 5 -#else -/* Avoid stack overflow, because we need to save part of page table */ -#define SWAP_RA_ORDER_CEILING 3 -#define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING) -#endif - -struct vma_swap_readahead { - unsigned short win; - unsigned short offset; - unsigned short nr_pte; -#ifdef CONFIG_64BIT - pte_t *ptes; -#else - pte_t ptes[SWAP_RA_PTE_CACHE_SIZE]; -#endif -}; - static inline swp_entry_t folio_swap_entry(struct folio *folio) { swp_entry_t entry = { .val = page_private(&folio->page) }; diff --git a/mm/swap_state.c b/mm/swap_state.c index ef32353c18a6..a33c60e0158f 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -709,6 +709,14 @@ void exit_swap_address_space(unsigned int type) swapper_spaces[type] = NULL; } +#define SWAP_RA_ORDER_CEILING 5 + +struct vma_swap_readahead { + unsigned short win; + unsigned short offset; + unsigned short nr_pte; +}; + static void swap_ra_info(struct vm_fault *vmf, struct vma_swap_readahead *ra_info) { @@ -716,11 +724,7 @@ static void swap_ra_info(struct vm_fault *vmf, unsigned long ra_val; unsigned long faddr, pfn, fpfn, lpfn, rpfn; unsigned long start, end; - pte_t *pte, *orig_pte; unsigned int max_win, hits, prev_win, win; -#ifndef CONFIG_64BIT - pte_t *tpte; -#endif max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster), SWAP_RA_ORDER_CEILING); @@ -739,12 +743,9 @@ static void swap_ra_info(struct vm_fault *vmf, max_win, prev_win); atomic_long_set(&vma->swap_readahead_info, SWAP_RA_VAL(faddr, win, 0)); - if (win == 1) return; - /* Copy the PTEs because the page table may be unmapped */ - orig_pte = pte = pte_offset_map(vmf->pmd, faddr); if (fpfn == pfn + 1) { lpfn = fpfn; rpfn = fpfn + win; @@ -764,15 +765,6 @@ static void swap_ra_info(struct vm_fault *vmf, ra_info->nr_pte = end - start; ra_info->offset = fpfn - start; - pte -= ra_info->offset; -#ifdef CONFIG_64BIT - ra_info->ptes = pte; -#else - tpte = ra_info->ptes; - for (pfn = start; pfn != end; pfn++) - *tpte++ = *pte++; -#endif - pte_unmap(orig_pte); } /** @@ -796,7 +788,8 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, struct swap_iocb *splug = NULL; struct vm_area_struct *vma = vmf->vma; struct page *page; - pte_t *pte, pentry; + pte_t *pte = NULL, pentry; + unsigned long addr; swp_entry_t entry; unsigned int i; bool page_allocated; @@ -808,17 +801,25 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, if (ra_info.win == 1) goto skip; + addr = vmf->address - (ra_info.offset * PAGE_SIZE); + blk_start_plug(&plug); - for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte; - i++, pte++) { - pentry = *pte; + for (i = 0; i < ra_info.nr_pte; i++, addr += PAGE_SIZE) { + if (!pte++) { + pte = pte_offset_map(vmf->pmd, addr); + if (!pte) + break; + } + pentry = ptep_get_lockless(pte); if (!is_swap_pte(pentry)) continue; entry = pte_to_swp_entry(pentry); if (unlikely(non_swap_entry(entry))) continue; + pte_unmap(pte); + pte = NULL; page = __read_swap_cache_async(entry, gfp_mask, vma, - vmf->address, &page_allocated); + addr, &page_allocated); if (!page) continue; if (page_allocated) { @@ -830,6 +831,8 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, } put_page(page); } + if (pte) + pte_unmap(pte); blk_finish_plug(&plug); swap_read_unplug(splug); lru_add_drain();